- SQL powered by Apache DataFusion
- Secondary indexes for vector search, full-text search, and scalar filters
- Computed columns with on-demand or scheduled refresh
- Materialized views with on-demand or scheduled refresh
- Time travel and versioning to pin and revisit datasets
- Search: vector, full-text, and hybrid, with filters and reranking
- Functions for custom transformations and model inference (early access)
- Row-level random access for retrieval and training
- Column additions without rewriting existing columns
Introduction
LanceDB
Multimodal lakehouse for AI.
LanceDB Enterprise is a distributed multimodal lakehouse for AI. It gives you one data layer for search and
retrieval, curation, feature engineering, and model training. It is built on Lance, an open-source
columnar format for multimodal AI data. For the open-source retrieval library that runs inside your application,
see LanceDB Embedded.
LanceDB Enterprise depends only on object storage for its primary state, and NVMe/memory for caching in the serving
layer, giving it the latency profile of an in-memory database with the petabyte scalability and cost profile of S3.
It brings these workloads into one system, giving your team one system to become expert in and removing the need
for multiple database systems and synchronization pipelines between them.
Core features include:
Was this page helpful?